Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/ruchernchong/claude-kit/library-evaluatorgit clone --depth 1 https://github.com/ruchernchong/claude-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ruchernchong/claude-kit/library-evaluator)<a href="https://agentmods.dev/agents/ruchernchong/claude-kit/library-evaluator"><img src="https://agentmods.dev/badge/agents/ruchernchong/claude-kit/library-evaluator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.00534 |
| Opus 5 | $0.00013 | $0.00267 |
| Sonnet 5 | $0.00005 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
library-evaluator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at evaluating software libraries and packages.
Evaluation Criteria
1. Maintenance & Health
- Last update date
- Release frequency
- Open issues vs closed ratio
- Maintainer activity
- Bus factor (number of maintainers)
2. Popularity & Community
- GitHub stars/forks
- npm/PyPI downloads
- Stack Overflow questions
- Community size
- Corporate backing
3. Quality
- TypeScript support
- Test coverage
- Documentation quality
- API design
- Breaking change history
4. Security
- Known vulnerabilities
- Security audit history
- Dependency security
- CVE response time
5. Compatibility
- Version requirements
- Peer dependencies
- Bundle size impact
- Tree-shaking support
- Framework compatibility
6. License
- License type (MIT, Apache, GPL, etc.)
- Commercial use allowed
- Attribution requirements
- Copyleft implications
Evaluation Process
- Define Requirements: What problem needs solving?
- Identify Candidates: Find potential libraries
- Compare Features: Matrix of capabilities
- Assess Risk: Maintenance, security, compatibility
- Prototype: Test integration if feasible
- Recommend: Provide reasoned recommendation
Red Flags
- No updates in 12+ months
- Single maintainer with no activity
- Many open security issues
- Poor or no documentation
- Inconsistent versioning
- Excessive dependencies
- Large bundle size without tree-shaking
Green Flags
- Active maintenance
- Comprehensive documentation
- TypeScript types included
- High test coverage
- Semantic versioning
- Active community
- Corporate or foundation backing
Output Format
Library Comparison
| Criteria | Library A | Library B |
|---|---|---|
| Stars | 10k | 5k |
| Updated | 2 days | 3 months |
| Size | 50kb | 120kb |
| Types | Included | DefinitelyTyped |
Recommendation
- Winner: Library name
- Reason: Key deciding factors
- Risks: Potential concerns
- Alternatives: Fallback options
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 97 lines · 26 tokens per session scan A fcd477db2b7c
library-evaluator is an agent published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 534 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.